
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
data = pd.read_csv("US_youtube_trending_data.csv")
print(data.shape)
data.head()

(199190, 16)


import json
category_info = json.load(open("US_category_id.json"))
print(category_info.keys())
category_info['items'][:5]

dict_keys(['kind', 'etag', 'items'])

[{'kind': 'youtube#videoCategory',
  'etag': 'IfWa37JGcqZs-jZeAyFGkbeh6bc',
  'id': '1',
  'snippet': {'title': 'Film & Animation',
   'assignable': True,
   'channelId': 'UCBR8-60-B28hp2BmDPdntcQ'}},
 {'kind': 'youtube#videoCategory',
  'etag': '5XGylIs7zkjHh5940dsT5862m1Y',
  'id': '2',
  'snippet': {'title': 'Autos & Vehicles',
   'assignable': True,
   'channelId': 'UCBR8-60-B28hp2BmDPdntcQ'}},
 {'kind': 'youtube#videoCategory',
  'etag': 'HCjFMARbBeWjpm6PDfReCOMOZGA',
  'id': '10',
  'snippet': {'title': 'Music',
   'assignable': True,
   'channelId': 'UCBR8-60-B28hp2BmDPdntcQ'}},
 {'kind': 'youtube#videoCategory',
  'etag': 'ra8H7xyAfmE2FewsDabE3TUSq10',
  'id': '15',
  'snippet': {'title': 'Pets & Animals',
   'assignable': True,
   'channelId': 'UCBR8-60-B28hp2BmDPdntcQ'}},
 {'kind': 'youtube#videoCategory',
  'etag': '7mqChSJogdF3hSIL-88BfDE-W8M',
  'id': '17',
  'snippet': {'title': 'Sports',
   'assignable': True,
   'channelId': 'UCBR8-60-B28hp2BmDPdntcQ'}}]


categories = {}
for entry in category_info["items"]:
    categories[entry["id"]] = entry["snippet"]["title"]
print(categories)

{'1': 'Film & Animation', '2': 'Autos & Vehicles', '10': 'Music', '15': 'Pets & Animals', '17': 'Sports', '18': 'Short Movies', '19': 'Travel & Events', '20': 'Gaming', '21': 'Videoblogging', '22': 'People & Blogs', '23': 'Comedy', '24': 'Entertainment', '25': 'News & Politics', '26': 'Howto & Style', '27': 'Education', '28': 'Science & Technology', '29': 'Nonprofits & Activism', '30': 'Movies', '31': 'Anime/Animation', '32': 'Action/Adventure', '33': 'Classics', '34': 'Comedy', '35': 'Documentary', '36': 'Drama', '37': 'Family', '38': 'Foreign', '39': 'Horror', '40': 'Sci-Fi/Fantasy', '41': 'Thriller', '42': 'Shorts', '43': 'Shows', '44': 'Trailers'}


data["category_title"] = data["categoryId"].map(lambda ID: categories[str(ID)])
data.head(5)


data.dtypes

video_id             object
title                object
publishedAt          object
channelId            object
channelTitle         object
categoryId            int64
trending_date        object
tags                 object
view_count            int64
likes                 int64
dislikes              int64
comment_count         int64
thumbnail_link       object
comments_disabled      bool
ratings_disabled       bool
description          object
category_title       object
dtype: object


data["publishedAt"] = pd.to_datetime(data["publishedAt"])
data["trending_date"] = pd.to_datetime(data["trending_date"])


print(data["publishedAt"].dtype)
print(data["trending_date"].dtype)

datetime64[ns, UTC]
datetime64[ns, UTC]


sort = data.sort_values("view_count", ascending = False)
sort.head(10)


data.sort_values("trending_date", ascending = False)
data.head()


sort.head(25)["tags"]

152788    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
152568    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
152365    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
152175    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
56374                       BIGHIT|빅히트|방탄소년단|BTS|BANGTAN|방탄
151968    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
151773    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
151570    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
151372    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
151167    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
150968    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
3358                        BIGHIT|빅히트|방탄소년단|BTS|BANGTAN|방탄
150758    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
150544    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
3137                        BIGHIT|빅히트|방탄소년단|BTS|BANGTAN|방탄
150335    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
150128    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
2894                        BIGHIT|빅히트|방탄소년단|BTS|BANGTAN|방탄
149917    YG Entertainment|YG|와이지|K-pop|BLACKPINK|블랙핑크|블...
73564                                                [None]
73361                                                [None]
73162                                                [None]
72959                                                [None]
72751                                                [None]
2653                        BIGHIT|빅히트|방탄소년단|BTS|BANGTAN|방탄
Name: tags, dtype: object


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(data["publishedAt"]), np.array(data["view_count"]))
plt.ylabel("Viewcount")
plt.xlabel("Time")
plt.title("Viewcount over time")
plt.show()


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(data["view_count"]), np.array(data["likes"]))
plt.xlabel("Viewcount")
plt.ylabel("Likes")
plt.title("Viewcount and Likes")
plt.show()


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(data["view_count"]), np.array(data["dislikes"]))
plt.xlabel("Viewcount")
plt.ylabel("Dislikes")
plt.title("Viewcount and Disikes")
plt.show()


grouped = data.groupby(["title"])
print(data.shape)
grouped.ngroups

(199190, 17)

37251


# with assistance from https://stackoverflow.com/questions/53842287/select-rows-with-highest-value-from-groupby
unique=data.loc[grouped["view_count"].idxmax()]
unique


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(unique["publishedAt"]), np.array(unique["view_count"]))
plt.ylabel("Viewcount")
plt.xlabel("Time")
plt.title("Viewcount over time")
plt.show()


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(unique["view_count"]), np.array(unique["likes"]))
plt.xlabel("Viewcount")
plt.ylabel("Likes")
plt.title("Viewcount and Likes")
plt.show()


plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(unique["view_count"]), np.array(unique["dislikes"]))
plt.xlabel("Viewcount")
plt.ylabel("Dislikes")
plt.title("Viewcount and Disikes")
plt.show()


plt.figure(figsize=(20,13))
plot = sns.scatterplot(x='publishedAt', y='view_count', data=unique, hue='category_title')
plt.legend(title='Category', bbox_to_anchor=(1.0, 1.0), loc="upper left")
plt.ylabel("Viewcount")
plt.xlabel("Time")
plt.title("Viewcount over time")
plt.show()
plt.figure(figsize=(20,13))
plot = sns.scatterplot(x='view_count', y='likes', data=unique, hue='category_title')
plt.legend(title='Category', bbox_to_anchor=(1.0, 1.0), loc="upper left")
plt.xlabel("Viewcount")
plt.ylabel("Likes")
plt.title("Viewcount and Likes")
plt.show()
plt.figure(figsize=(20,13))
plot = sns.scatterplot(x='view_count', y='dislikes', data=unique, hue='category_title')
plt.legend(title='Category', bbox_to_anchor=(1.0, 1.0), loc="upper left")
plt.xlabel("Viewcount")
plt.ylabel("Dislikes")
plt.title("Viewcount and Disikes")
plt.show()


print(pd.unique(unique["category_title"]))

['Entertainment' 'Sports' 'Education' 'Music' 'Film & Animation'
 'Science & Technology' 'People & Blogs' 'Comedy' 'Gaming'
 'Travel & Events' 'News & Politics' 'Autos & Vehicles' 'Howto & Style'
 'Pets & Animals' 'Nonprofits & Activism']


unique['category_title'].value_counts()

category_title
Gaming                   7467
Entertainment            7274
Music                    5839
Sports                   4623
People & Blogs           3255
Comedy                   1880
Film & Animation         1394
News & Politics          1369
Science & Technology     1140
Howto & Style             996
Education                 902
Autos & Vehicles          732
Travel & Events           205
Pets & Animals            157
Nonprofits & Activism      18
Name: count, dtype: int64


sorted_unique = unique.sort_values(by="view_count", ascending=False)
sorted_unique.head(50)


from wordcloud import WordCloud

text2020 = " ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2020].tags)
word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2020)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()

text2021 = " ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2021].tags)
word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2021)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()
text2022 = " ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2022].tags)

word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2022)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()


from wordcloud import WordCloud
plt.figure(figsize=(20,10))
text2020 = (" ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2020].tags)).replace('[None]', '')
word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2020)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()
plt.figure(figsize=(20,10))
text2021 = (" ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2021].tags)).replace('[None]', '')
word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2021)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()
text2022 = (" ".join(cat.split("|")[0] for cat in data.loc[data["publishedAt"].dt.year == 2022].tags)).replace('[None]', '')
plt.figure(figsize=(20,10))
word_cloud = WordCloud(collocations = False, background_color = 'white').generate(text2022)
# Display the generated Word Cloud
plt.imshow(word_cloud, interpolation='bilinear')
plt.axis("off")
plt.show()


channel_cumulative_sums=unique.groupby(["channelTitle"])["view_count"].sum().sort_values(ascending=False)
channel_cumulative_sums_as_frame = channel_cumulative_sums.to_frame()
channel_cumulative_sums_as_frame["channelTitle"] = channel_cumulative_sums_as_frame.index
channel_cumulative_sums_as_frame = channel_cumulative_sums_as_frame.drop(columns="channelTitle")
temp = channel_cumulative_sums_as_frame.reset_index().head(50)
unique_for_image =unique.groupby(["channelId"])["view_count"].sum().sort_values(ascending=False).to_frame()
temp["channelId"] = unique_for_image.reset_index().head(50)["channelId"]
temp.head(20)


a = unique.loc[unique["publishedAt"].dt.year == 2022]
a = a["channelTitle"].value_counts().sort_index()
occ_count = pd.DataFrame({"channelTitle": a.index, "occurences": a.values})
occ_count = occ_count.sort_values(by="occurences", ascending=False)
#trim to top 100
occ_count = occ_count.head(100)
#add channelId -  by looking up in unique
occ_count["channelId"] = occ_count.apply(lambda row: unique.loc[unique["channelTitle"] == row["channelTitle"]]["channelId"].iloc[0], axis=1)
occ_count.head(20)


import requests
import os
if not os.path.exists("images"):
    print("Making images directory")
    
    os.mkdir("images")
    unique_for_image =unique.groupby(["channelId"])["view_count"].sum().sort_values(ascending=False).to_frame()
    unique_for_image["channelId"] = unique_for_image.index

    first50 = unique_for_image["channelId"].head(50).to_csv( header=None, index=None).strip('\n').replace("\r", "") .replace("\n", ",")
    z = requests.get('https://www.googleapis.com/youtube/v3/channels?part=snippet&id='+first50+'&fields=items(id%2Csnippet%2Fthumbnails)&key=AIzaSyBzTEil14Vsa_8W64NCr98X-snvPapD2wo')
    data = z.json()
    for item in data["items"]:
        img_data = requests.get(item["snippet"]["thumbnails"]["default"]["url"]).content
        with open('images/'+item["id"]+'.jpg', 'wb') as handler:
            handler.write(img_data)


first50 = occ_count["channelId"].iloc[:50].to_csv( header=None, index=None).strip('\n').replace("\r", "") .replace("\n", ",")
z = requests.get('https://www.googleapis.com/youtube/v3/channels?part=snippet&id='+first50+'&fields=items(id%2Csnippet%2Fthumbnails)&key=AIzaSyBzTEil14Vsa_8W64NCr98X-snvPapD2wo')
data = z.json()
for item in data["items"]:
    img_data = requests.get(item["snippet"]["thumbnails"]["default"]["url"]).content
    with open('images/'+item["id"]+'.jpg', 'wb') as handler:
        handler.write(img_data)
#split request into 2 groups -  google api does not allow more than 50 ids per request
second50 = occ_count["channelId"].iloc[50:100].to_csv( header=None, index=None).strip('\n').replace("\r", "") .replace("\n", ",")
z = requests.get('https://www.googleapis.com/youtube/v3/channels?part=snippet&id='+second50+'&fields=items(id%2Csnippet%2Fthumbnails)&key=AIzaSyBzTEil14Vsa_8W64NCr98X-snvPapD2wo')
data = z.json()
for item in data["items"]:
    img_data = requests.get(item["snippet"]["thumbnails"]["default"]["url"]).content
    with open('images/'+item["id"]+'.jpg', 'wb') as handler:
        handler.write(img_data)


# Code from https://stackoverflow.com/questions/51486297/cropping-an-image-in-a-circular-way-using-python
from PIL import Image, ImageDraw

ids = temp['channelId'].iloc[::-1]

for id in ids:
    # Open the input image as numpy array, convert to RGB
    img=Image.open('images/'+id+'.jpg').convert("RGB")
    npImage=np.array(img)
    h,w=img.size

    # Create same size alpha layer with circle
    alpha = Image.new('L', img.size,0)
    draw = ImageDraw.Draw(alpha)
    draw.pieslice([0,0,h,w],0,360,fill=255)

    # Convert alpha Image to numpy array
    npAlpha=np.array(alpha)

    # Add alpha layer to RGB
    npImage=np.dstack((npImage,npAlpha))

    # Save with alpha
    Image.fromarray(npImage).save('images/'+id+'.png')


ids =occ_count['channelId'].iloc[:100]

for id in ids:
    # Open the input image as numpy array, convert to RGB
    img=Image.open('images/'+id+'.jpg').convert("RGB")
    npImage=np.array(img)
    h,w=img.size

    # Create same size alpha layer with circle
    alpha = Image.new('L', img.size,0)
    draw = ImageDraw.Draw(alpha)
    draw.pieslice([0,0,h,w],0,360,fill=255)

    # Convert alpha Image to numpy array
    npAlpha=np.array(alpha)

    # Add alpha layer to RGB
    npImage=np.dstack((npImage,npAlpha))

    # Save with alpha
    Image.fromarray(npImage).save('images/'+id+'.png')


# Code taken from https://www.python-graph-gallery.com/circular-packing-1-level-hierarchy, slightly modified
import circlify
circles = circlify.circlify(
    temp["view_count"].tolist(), 
    show_enclosure=False, 
    target_enclosure=circlify.Circle(x=0, y=0, r=1)
)

# import libraries
import circlify
import matplotlib.pyplot as plt

# Create just a figure and only one subplot
fig, ax = plt.subplots(figsize=(20,20))

# Title
ax.set_title('Top 50 Channels by Cumulative Viewcount of Trending Videos in 2022')

# Remove axes
ax.axis('off')

# Find axis boundaries
lim = max(
    max(
        abs(circle.x) + circle.r,
        abs(circle.y) + circle.r,
    )
    for circle in circles
)
plt.xlim(-lim, lim)
plt.ylim(-lim, lim)

# list of labels
labels = temp['channelTitle'].iloc[::-1]
ids = temp['channelId'].iloc[::-1]

# print circles
for circle, label, ids in zip(circles, labels, ids):
    x, y, r = circle
    ax.add_patch(plt.Circle((x, y), r, alpha=1, linewidth=2, edgecolor='black', facecolor='none'))
    #plt.annotate(label,   (x,y ) , va='center',  ha='center', fontsize=7, fontweight='bold')
    # load the image
    img = plt.imread('images/'+ids+'.png')
    
    # add the image as an annotation
    ax.imshow(img, extent=[x-r, x+r, y-r, y+r], alpha=1)


circles = circlify.circlify(
    occ_count["occurences"].tolist(), 
    show_enclosure=False, 
    target_enclosure=circlify.Circle(x=0, y=0, r=1)
)

# import libraries
import circlify
import matplotlib.pyplot as plt

# Create just a figure and only one subplot
fig, ax = plt.subplots(figsize=(20,20))

# Title
ax.set_title('Top 100 Channels by Occurences of Videos in Trending in 2022')

# Remove axes
ax.axis('off')

# Find axis boundaries
lim = max(
    max(
        abs(circle.x) + circle.r,
        abs(circle.y) + circle.r,
    )
    for circle in circles
)
plt.xlim(-lim, lim)
plt.ylim(-lim, lim)

# list of labels
labels = occ_count['channelTitle'].iloc[::-1]
ids = occ_count['channelId'].iloc[::-1]

# print circles
for circle, label, ids in zip(circles, labels, ids):
    x, y, r = circle
    ax.add_patch(plt.Circle((x, y), r, alpha=1, linewidth=2, edgecolor='black', facecolor='none'))
    #plt.annotate(label,   (x,y ) , va='center',  ha='center', fontsize=7, fontweight='bold')
    # load the image
    img = plt.imread('images/'+ids+'.png')
    
    # add the image as an annotation
    ax.imshow(img, extent=[x-r, x+r, y-r, y+r], alpha=1)


from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
from sklearn import metrics
tree = DecisionTreeClassifier(max_depth = 10)
X = unique[["view_count", "likes"]]


y= unique["categoryId"].astype("int")
# from https://www.datacamp.com/tutorial/decision-tree-classification-python
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)


# from https://www.datacamp.com/tutorial/decision-tree-classification-python
tree = tree.fit(X_train,y_train)
#Predict the response for test dataset
y_pred = tree.predict(X_test)
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.29098067287043666


# from https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(max_depth = 15, random_state=0)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)

print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.29142806012884753


# from https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html
from sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier(n_neighbors=100)
neigh.fit(X_train, y_train)
y_pred = neigh.predict(X_test)
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

Accuracy: 0.29205440229062274


from sklearn.inspection import DecisionBoundaryDisplay
def graph_boundary(model):
    fig = plt.figure(figsize=(20,10))
    ax = fig.add_subplot(111)
    DecisionBoundaryDisplay.from_estimator(
        model, X_train, alpha=0.8, eps=0.5, ax= ax
    )
    sns.scatterplot(
        x=X["view_count"],
        y=X["likes"],
        hue=y,
        alpha=1.0,
        edgecolor="black",
    )
    plt.xlabel("Viewcount")
    plt.ylabel("Likes")
graph_boundary(tree)
plt.title("Decision Tree")
plt.show()
graph_boundary(clf)
plt.title("Random Forest")
plt.show()
graph_boundary(neigh)
plt.title("K Nearest Neighbors")
plt.show()


unique["TimeDiff"] = (unique["trending_date"] - unique["publishedAt"]).dt.days
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(unique["TimeDiff"]), np.array(unique["view_count"]))
plt.ylabel("View Count")
plt.xlabel("Time Between Trending and Release (In Days)")
plt.title("Views Versus Time Difference")
plt.show()


a = unique["channelTitle"].value_counts().sort_index()
occ_count = pd.DataFrame({"channelTitle": a.index,
                         "occurences": a.values})


result = unique.groupby('channelTitle')['view_count'].median()
occ_count_med = pd.merge(result, occ_count, on = "channelTitle")
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(occ_count_med["view_count"]), np.array(occ_count_med["occurences"]))
plt.ylabel("Occ")
plt.xlabel("ViewCount")

for i, row in occ_count_med.iterrows():
    if row['view_count'] > 100000000 or row['occurences'] > 100 or row["channelTitle"] == "MrBeast":
        plt.annotate(row['channelTitle'], (row['view_count'], row['occurences']))

plt.title("Median Video Viewcount vs Occurrences in Trending By Channel")

plt.show()


result = unique.groupby('channelTitle')['view_count'].max()
occ_count_max = pd.merge(result, occ_count, on = "channelTitle")
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(occ_count_max["view_count"]), np.array(occ_count_max["occurences"]))
plt.ylabel("Occ")
plt.xlabel("ViewCount")
plt.title("Maximum Video Viewcount vs Occurrences in Trending By Channel")

for i, row in occ_count_max.iterrows():
    if row['view_count'] > 130000000 or row['occurences'] > 80:
        plt.annotate(row['channelTitle'], (row['view_count'], row['occurences']))


result = unique.groupby('channelTitle')['likes'].median()
like_count_med = pd.merge(result, occ_count, on = "channelTitle")
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(like_count_med["likes"]), np.array(like_count_med["occurences"]))
plt.ylabel("Occ")
plt.xlabel("Likes")
plt.title("Median Video Likes vs Occurrences in Trending By Channel")

for i, row in like_count_med.iterrows():
    if row['likes'] > 3000000 or row['occurences'] > 80:
        plt.annotate(row['channelTitle'], (row['likes'], row['occurences']))


result = unique.groupby('channelTitle')['comment_count'].median()
comm_count_med = pd.merge(result, occ_count, on = "channelTitle")
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(comm_count_med["comment_count"]), np.array(comm_count_med["occurences"]))
plt.ylabel("Occ")
plt.xlabel("Comments")
plt.title("Median Video Comments vs Occurrences in Trending By Channel")

for i, row in comm_count_med.iterrows():
    if row['comment_count'] > 1000000 or row['occurences'] > 80:
        plt.annotate(row['channelTitle'], (row['comment_count'], row['occurences']))


result = unique.groupby('channelTitle')['TimeDiff'].median()
result = pd.DataFrame({"channelTitle": result.index,
                         "TimeDiff": result.values})

view = unique.groupby('channelTitle')['view_count'].mean()
occ_count_max = pd.merge(result, view, on = "channelTitle")

plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(occ_count_max["TimeDiff"]), np.array(occ_count_max["view_count"]))
plt.ylabel("Median ViewCount")
plt.xlabel("TimeDiff")

for i, row in occ_count_max.iterrows():
    if row['view_count'] > 80000000 or row['TimeDiff'] >31 or row["channelTitle"] == "NBA" or row["channelTitle"] == "NFL"or row["channelTitle"] == "NBC Sports" or row["channelTitle"] == "SSundee":
        plt.annotate(row['channelTitle'], (row['TimeDiff'], row['view_count']))


sports = unique[unique["categoryId"] == 17]

result = sports.groupby('channelTitle')['view_count'].median()
view_count_med = pd.merge(result, occ_count, on = "channelTitle")
plt.figure(figsize=(20,10))
plot = plt.scatter(np.array(view_count_med["view_count"]), np.array(view_count_med["occurences"]))
plt.ylabel("Occ")
plt.xlabel("Views")
plt.title("Median Views vs Occurrences in Trending By Channel for Sports")

for i, row in view_count_med.iterrows():
    if row['view_count'] > 10000000 or row['occurences'] > 80 or (row['view_count'] > 6000000 and row['occurences'] > 50):
        plt.annotate(row['channelTitle'], (row['view_count'], row['occurences']))


import sklearn
import sklearn.preprocessing
import sklearn.svm
import sklearn.model_selection
import sklearn.linear_model
from sklearn.linear_model import LinearRegression
import statsmodels.formula.api as smf
reg = LinearRegression().fit((np.array(unique["view_count"])).reshape(-1, 1), unique["likes"])
pred_line = reg.predict(np.array(unique["view_count"]).reshape(-1, 1))

ols1 = smf.ols(formula="likes ~ view_count ", data=unique).fit()
print(ols1.summary())

plt.figure(figsize=(20,10))
unique["1st_pred"] = pred_line
plot1 = plt.plot(np.array(unique["view_count"]), np.array(pred_line), color="red")

plot = sns.scatterplot(data=unique, x='view_count', y='likes')
plot.set(
       ylabel='likes',
       title='Viewcount Versus Likes')

plt.show()

                            OLS Regression Results                            
==============================================================================
Dep. Variable:                  likes   R-squared:                       0.727
Model:                            OLS   Adj. R-squared:                  0.727
Method:                 Least Squares   F-statistic:                 9.929e+04
Date:                Fri, 12 May 2023   Prob (F-statistic):               0.00
Time:                        22:32:16   Log-Likelihood:            -5.0630e+05
No. Observations:               37251   AIC:                         1.013e+06
Df Residuals:                   37249   BIC:                         1.013e+06
Df Model:                           1                                         
Covariance Type:            nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept    901.9685   1075.362      0.839      0.402   -1205.770    3009.707
view_count     0.0477      0.000    315.109      0.000       0.047       0.048
==============================================================================
Omnibus:                    39416.070   Durbin-Watson:                   1.280
Prob(Omnibus):                  0.000   Jarque-Bera (JB):         28642151.353
Skew:                           4.501   Prob(JB):                         0.00
Kurtosis:                     138.545   Cond. No.                     7.63e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 7.63e+06. This might indicate that there are
strong multicollinearity or other numerical problems.


reg = LinearRegression().fit((np.array(unique["view_count"])).reshape(-1, 1), unique["comment_count"])
pred_line = reg.predict(np.array(unique["view_count"]).reshape(-1, 1))

ols1 = smf.ols(formula="comment_count ~ view_count ", data=unique).fit()
print(ols1.summary())

plt.figure(figsize=(20,10))
unique["1st_pred"] = pred_line
plot1 = plt.plot(np.array(unique["view_count"]), np.array(pred_line), color="red")

plot = sns.scatterplot(data=unique, x='view_count', y='comment_count')
plot.set(
       ylabel='comments',
       title='Viewcount Versus Comment Count')

plt.show()

                            OLS Regression Results                            
==============================================================================
Dep. Variable:          comment_count   R-squared:                       0.353
Model:                            OLS   Adj. R-squared:                  0.353
Method:                 Least Squares   F-statistic:                 2.032e+04
Date:                Fri, 12 May 2023   Prob (F-statistic):               0.00
Time:                        22:32:17   Log-Likelihood:            -4.6271e+05
No. Observations:               37251   AIC:                         9.254e+05
Df Residuals:                   37249   BIC:                         9.254e+05
Df Model:                           1                                         
Covariance Type:            nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept  -7685.8342    333.680    -23.034      0.000   -8339.857   -7031.811
view_count     0.0067   4.69e-05    142.541      0.000       0.007       0.007
==============================================================================
Omnibus:                   108202.043   Durbin-Watson:                   1.864
Prob(Omnibus):                  0.000   Jarque-Bera (JB):      12057366999.812
Skew:                          39.972   Prob(JB):                         0.00
Kurtosis:                    2789.020   Cond. No.                     7.63e+06
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 7.63e+06. This might indicate that there are
strong multicollinearity or other numerical problems.


unique["min_date"] = unique["trending_date"].min()
unique["daydiff"] = (unique["trending_date"] - unique["min_date"]).dt.days


reg = LinearRegression().fit((np.array(unique["view_count"])).reshape(-1, 1), unique["daydiff"])
pred_line = reg.predict(np.array(unique["daydiff"]).reshape(-1, 1))

ols1 = smf.ols(formula="view_count ~ daydiff ", data=unique).fit()
print(ols1.summary())

plt.figure(figsize=(20,10))
unique["1st_pred"] = pred_line
plot1 = plt.plot(np.array(unique["daydiff"]), np.array(pred_line), color="red")

plot = sns.scatterplot(data=unique, x='daydiff', y='view_count')
plot.set(
       xlabel = 'Days Since Beginning of Data',
       ylabel='View Count',
       title='Viewcount Versus Time')

plt.show()

                            OLS Regression Results                            
==============================================================================
Dep. Variable:             view_count   R-squared:                       0.003
Model:                            OLS   Adj. R-squared:                  0.003
Method:                 Least Squares   F-statistic:                     115.0
Date:                Fri, 12 May 2023   Prob (F-statistic):           8.63e-27
Time:                        22:32:17   Log-Likelihood:            -6.3788e+05
No. Observations:               37251   AIC:                         1.276e+06
Df Residuals:                   37249   BIC:                         1.276e+06
Df Model:                           1                                         
Covariance Type:            nonrobust                                         
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
Intercept   3.234e+06   7.02e+04     46.070      0.000     3.1e+06    3.37e+06
daydiff    -1302.1094    121.425    -10.724      0.000   -1540.105   -1064.114
==============================================================================
Omnibus:                    70249.421   Durbin-Watson:                   1.649
Prob(Omnibus):                  0.000   Jarque-Bera (JB):        197388673.277
Skew:                          14.338   Prob(JB):                         0.00
Kurtosis:                     358.459   Cond. No.                     1.18e+03
==============================================================================

Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.18e+03. This might indicate that there are
strong multicollinearity or other numerical problems.

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description
0	3C66w5Z0ixs	I ASKED HER TO BE MY GIRLFRIEND...	2020-08-11T19:20:14Z	UCvtRTOMP2TqYqu51xNrqAzg	Brawadis	22	2020-08-12T00:00:00Z	brawadis\|prank\|basketball\|skits\|ghost\|funny vi...	1514614	156908	5855	35313	https://i.ytimg.com/vi/3C66w5Z0ixs/default.jpg	False	False	SUBSCRIBE to BRAWADIS ▶ http://bit.ly/Subscrib...
1	M9Pmf9AB4Mo	Apex Legends \| Stories from the Outlands – “Th...	2020-08-11T17:00:10Z	UC0ZV6M2THA81QT9hrVWJG3A	Apex Legends	20	2020-08-12T00:00:00Z	Apex Legends\|Apex Legends characters\|new Apex ...	2381688	146739	2794	16549	https://i.ytimg.com/vi/M9Pmf9AB4Mo/default.jpg	False	False	While running her own modding shop, Ramya Pare...
2	J78aPJ3VyNs	I left youtube for a month and THIS is what ha...	2020-08-11T16:34:06Z	UCYzPXprvl5Y-Sf0g4vX-m6g	jacksepticeye	24	2020-08-12T00:00:00Z	jacksepticeye\|funny\|funny meme\|memes\|jacksepti...	2038853	353787	2628	40221	https://i.ytimg.com/vi/J78aPJ3VyNs/default.jpg	False	False	I left youtube for a month and this is what ha...
3	kXLn3HkpjaA	XXL 2020 Freshman Class Revealed - Official An...	2020-08-11T16:38:55Z	UCbg_UMjlHJg_19SZckaKajg	XXL	10	2020-08-12T00:00:00Z	xxl freshman\|xxl freshmen\|2020 xxl freshman\|20...	496771	23251	1856	7647	https://i.ytimg.com/vi/kXLn3HkpjaA/default.jpg	False	False	Subscribe to XXL → http://bit.ly/subscribe-xxl...
4	VIUo6yapDbc	Ultimate DIY Home Movie Theater for The LaBran...	2020-08-11T15:10:05Z	UCDVPcEbVLQgLZX0Rt6jo34A	Mr. Kate	26	2020-08-12T00:00:00Z	The LaBrant Family\|DIY\|Interior Design\|Makeove...	1123889	45802	964	2196	https://i.ytimg.com/vi/VIUo6yapDbc/default.jpg	False	False	Transforming The LaBrant Family's empty white ...

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description	category_title
0	3C66w5Z0ixs	I ASKED HER TO BE MY GIRLFRIEND...	2020-08-11T19:20:14Z	UCvtRTOMP2TqYqu51xNrqAzg	Brawadis	22	2020-08-12T00:00:00Z	brawadis\|prank\|basketball\|skits\|ghost\|funny vi...	1514614	156908	5855	35313	https://i.ytimg.com/vi/3C66w5Z0ixs/default.jpg	False	False	SUBSCRIBE to BRAWADIS ▶ http://bit.ly/Subscrib...	People & Blogs
1	M9Pmf9AB4Mo	Apex Legends \| Stories from the Outlands – “Th...	2020-08-11T17:00:10Z	UC0ZV6M2THA81QT9hrVWJG3A	Apex Legends	20	2020-08-12T00:00:00Z	Apex Legends\|Apex Legends characters\|new Apex ...	2381688	146739	2794	16549	https://i.ytimg.com/vi/M9Pmf9AB4Mo/default.jpg	False	False	While running her own modding shop, Ramya Pare...	Gaming
2	J78aPJ3VyNs	I left youtube for a month and THIS is what ha...	2020-08-11T16:34:06Z	UCYzPXprvl5Y-Sf0g4vX-m6g	jacksepticeye	24	2020-08-12T00:00:00Z	jacksepticeye\|funny\|funny meme\|memes\|jacksepti...	2038853	353787	2628	40221	https://i.ytimg.com/vi/J78aPJ3VyNs/default.jpg	False	False	I left youtube for a month and this is what ha...	Entertainment
3	kXLn3HkpjaA	XXL 2020 Freshman Class Revealed - Official An...	2020-08-11T16:38:55Z	UCbg_UMjlHJg_19SZckaKajg	XXL	10	2020-08-12T00:00:00Z	xxl freshman\|xxl freshmen\|2020 xxl freshman\|20...	496771	23251	1856	7647	https://i.ytimg.com/vi/kXLn3HkpjaA/default.jpg	False	False	Subscribe to XXL → http://bit.ly/subscribe-xxl...	Music
4	VIUo6yapDbc	Ultimate DIY Home Movie Theater for The LaBran...	2020-08-11T15:10:05Z	UCDVPcEbVLQgLZX0Rt6jo34A	Mr. Kate	26	2020-08-12T00:00:00Z	The LaBrant Family\|DIY\|Interior Design\|Makeove...	1123889	45802	964	2196	https://i.ytimg.com/vi/VIUo6yapDbc/default.jpg	False	False	Transforming The LaBrant Family's empty white ...	Howto & Style

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description	category_title
152788	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-10 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	277791741	12993894	0	3534337	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
152568	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-09 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	273162966	12937252	0	3516745	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
152365	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-08 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	268758295	12882841	0	3504692	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
152175	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-07 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	264459017	12829059	0	3491132	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
56374	WMweEpGlu_U	BTS (방탄소년단) 'Butter' Official MV	2021-05-21 03:46:13+00:00	UC3IZKseVpdzPSBaWxBxundA	HYBE LABELS	10	2021-05-30 00:00:00+00:00	BIGHIT\|빅히트\|방탄소년단\|BTS\|BANGTAN\|방탄	264407389	16021534	150989	6738537	https://i.ytimg.com/vi/WMweEpGlu_U/default.jpg	False	False	BTS (방탄소년단) 'Butter' Official MV Credits: Dire...	Music
151968	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-06 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	260126694	12773474	0	3479717	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
151773	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-05 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	255524865	12715882	0	3466961	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
151570	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-04 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	250963177	12653408	0	3450920	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
151372	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-03 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	245994768	12577694	0	3438048	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
151167	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-02 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	240757307	12502699	0	3424014	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description	category_title
0	3C66w5Z0ixs	I ASKED HER TO BE MY GIRLFRIEND...	2020-08-11 19:20:14+00:00	UCvtRTOMP2TqYqu51xNrqAzg	Brawadis	22	2020-08-12 00:00:00+00:00	brawadis\|prank\|basketball\|skits\|ghost\|funny vi...	1514614	156908	5855	35313	https://i.ytimg.com/vi/3C66w5Z0ixs/default.jpg	False	False	SUBSCRIBE to BRAWADIS ▶ http://bit.ly/Subscrib...	People & Blogs
1	M9Pmf9AB4Mo	Apex Legends \| Stories from the Outlands – “Th...	2020-08-11 17:00:10+00:00	UC0ZV6M2THA81QT9hrVWJG3A	Apex Legends	20	2020-08-12 00:00:00+00:00	Apex Legends\|Apex Legends characters\|new Apex ...	2381688	146739	2794	16549	https://i.ytimg.com/vi/M9Pmf9AB4Mo/default.jpg	False	False	While running her own modding shop, Ramya Pare...	Gaming
2	J78aPJ3VyNs	I left youtube for a month and THIS is what ha...	2020-08-11 16:34:06+00:00	UCYzPXprvl5Y-Sf0g4vX-m6g	jacksepticeye	24	2020-08-12 00:00:00+00:00	jacksepticeye\|funny\|funny meme\|memes\|jacksepti...	2038853	353787	2628	40221	https://i.ytimg.com/vi/J78aPJ3VyNs/default.jpg	False	False	I left youtube for a month and this is what ha...	Entertainment
3	kXLn3HkpjaA	XXL 2020 Freshman Class Revealed - Official An...	2020-08-11 16:38:55+00:00	UCbg_UMjlHJg_19SZckaKajg	XXL	10	2020-08-12 00:00:00+00:00	xxl freshman\|xxl freshmen\|2020 xxl freshman\|20...	496771	23251	1856	7647	https://i.ytimg.com/vi/kXLn3HkpjaA/default.jpg	False	False	Subscribe to XXL → http://bit.ly/subscribe-xxl...	Music
4	VIUo6yapDbc	Ultimate DIY Home Movie Theater for The LaBran...	2020-08-11 15:10:05+00:00	UCDVPcEbVLQgLZX0Rt6jo34A	Mr. Kate	26	2020-08-12 00:00:00+00:00	The LaBrant Family\|DIY\|Interior Design\|Makeove...	1123889	45802	964	2196	https://i.ytimg.com/vi/VIUo6yapDbc/default.jpg	False	False	Transforming The LaBrant Family's empty white ...	Howto & Style

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description	category_title
29372	3BgG4bUDHa4	!@#$%$#!! \|\| Dubov vs Carlsen \|\| Airthings Mas...	2020-12-30 17:43:29+00:00	UCL5YbN5WLFD8dLIegT5QAbA	agadmator's Chess Channel	24	2021-01-09 00:00:00+00:00	agadmator\|chess\|best chess channel\|best youtub...	609588	25234	283	2186	https://i.ytimg.com/vi/3BgG4bUDHa4/default.jpg	False	False	Follow me on Instagram for extra content https...	Entertainment
64132	HFk73_EdK3o	#1 76ERS at #5 HAWKS \| FULL GAME HIGHLIGHTS \| ...	2021-06-17 02:45:41+00:00	UCWJ2lWNubArHWmf3FIHbfcQ	NBA	17	2021-06-21 00:00:00+00:00	Basketball\|G League\|NBA\|game-0042000205	1605052	16700	677	5527	https://i.ytimg.com/vi/HFk73_EdK3o/default.jpg	False	False	#1 76ERS at #5 HAWKS \| FULL GAME HIGHLIGHTS \| ...	Sports
112783	pIB3neebwSk	#1 Absolute Best Remedy for Dry and Wrinkled H...	2022-02-17 11:15:05+00:00	UC3w193M5tYPJqF0Hi-7U-2g	Dr. Eric Berg DC	27	2022-02-22 00:00:00+00:00	#1 Absolute Best Remedy for Dry and Wrinkled H...	1318126	45372	0	2872	https://i.ytimg.com/vi/pIB3neebwSk/default.jpg	False	False	Lotion may actually make your hands drier. Giv...	Education
23569	QY7ArP0ebaM	#1 Alabama Crimson Tide vs. LSU Tigers: Extend...	2020-12-06 05:05:49+00:00	UCja8sZ2T4ylIqjggA1Zuukg	CBS Sports HQ	17	2020-12-10 00:00:00+00:00	Alabama Crimson Tide\|LSU Tigers\|Alabama Crimso...	335967	1644	102	493	https://i.ytimg.com/vi/QY7ArP0ebaM/default.jpg	False	False	No. 1 Alabama leads LSU 52-17 after three quar...	Sports
87371	AtW81jzLx2o	#1 Alabama Vs Texas A&M Extended Highlights \| ...	2021-10-10 04:42:02+00:00	UCja8sZ2T4ylIqjggA1Zuukg	CBS Sports HQ	17	2021-10-16 00:00:00+00:00	college football\|Alabama\|roll tide\|Texas a&m\|A...	635561	5203	206	1228	https://i.ytimg.com/vi/AtW81jzLx2o/default.jpg	False	False	Extended highlights from Texas A&M upset over ...	Sports
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
134781	7UfiCa244XE	🥪 👜 Ma’amalade sandwich Your Majesty?	2022-06-06 12:32:01+00:00	UCTkC3Jt91QkqNAE4FGWkEIQ	The Royal Family	22	2022-06-12 00:00:00+00:00	[None]	3695044	106396	0	0	https://i.ytimg.com/vi/7UfiCa244XE/default.jpg	True	False	The Queen and Paddington Bear get the Platinum...	People & Blogs
63555	BNqg-1GBpLw	🥭Fresh Farm Fruit Eating \| Tiktok China \| Oddl...	2021-06-03 13:39:19+00:00	UCyEHvAVMP9yY0Gp0ndLnwEQ	Fruit Satisfying	22	2021-06-17 00:00:00+00:00	Tik Tok China\|farm fresh ninja fruit\|Fresh fru...	55054684	661233	47998	2087	https://i.ytimg.com/vi/BNqg-1GBpLw/default.jpg	False	False	Fresh Farm Fruit Eating on Orange Garden \| Odd...	People & Blogs
121377	VWo7X6RijrM	🥳How To UNLOCK THE FREE EXCLUSIVE EASY in Pe...	2022-04-01 17:18:08+00:00	UC5_pDWCrgnvP4YpWsWFPv7g	Sonsss	20	2022-04-06 00:00:00+00:00	sonsss\|new\|roblox\|sonsss pet sim x\|pet simulat...	875677	15328	0	2970	https://i.ytimg.com/vi/VWo7X6RijrM/default.jpg	False	False	🥳How To UNLOCK THE FREE EXCLUSIVE EASY in Pe...	Gaming
117943	ClSgM70C6r0	🦌 WOODLAND EGG UPDATE! 🌲 8 NEW PETS! 😲 Adopt M...	2022-03-16 18:00:12+00:00	UCVdPM7Dgxm3cHXM2ro__bUg	PlayAdoptMe	20	2022-03-20 00:00:00+00:00	adoptme\|playadoptme\|playadoptmeroblox\|adoptmer...	383351	23615	0	3298	https://i.ytimg.com/vi/ClSgM70C6r0/default.jpg	False	False	🥚 Woodland Egg Update! 🥚🦌 8 new woodsy creatur...	Gaming
116389	YSaE8OWwJZE	🦝Raccoon Powers 🦝\| Ep. 1 \| Afterlife Minecraft...	2022-03-04 17:30:03+00:00	UCzTlXb7ivVzuFlugVCv3Kvg	LDShadowLady	20	2022-03-12 00:00:00+00:00	ldshadowlady\|minecraft\|mini game\|girl gamer\|pi...	2132503	144402	0	8865	https://i.ytimg.com/vi/YSaE8OWwJZE/default.jpg	False	False	Please boop the like button if you enjoy the...	Gaming

Table of Contents¶

1: Data Collection ¶

2: Data Cleaning ¶

3: Exploratory Data Analysis ¶

4: Analysis, Hypothesis Testing, Machine Learning ¶

5: Conclusions ¶

Part 1: Data Collection¶

Introduction¶

Part 2: Data Cleaning¶

Part 3: Exploratory Data Analysis¶

Preliminary Graphs¶

Top 50 Videos¶

Word Cloud¶

Circle Packing Chart¶

Data Collection: Profile Picture Extraction from Youtube API¶

Data Cleanup: Cropping Images¶

Graphing¶

Part 4: Analysis, Hypothesis Testing and Machine Learning¶

Classification¶

Comparing Likes, Viewcount, and Comments¶

Part 5: Conclusions¶

	channelTitle	view_count	channelId
0	MrBeast	2526660908	UCX6OQ3DkcsbYNE6H8uQQuVA
1	BLACKPINK	1912983541	UC3IZKseVpdzPSBaWxBxundA
2	HYBE LABELS	1532484746	UCOmHUn--16B90oW2L6FRR3A
3	SMTOWN	1369848949	UCEf_Bc-KVd7onSeifS3py9g
4	JYP Entertainment	1335988975	UCaO6TYtlC8U5ttz62hTrZgg
5	NFL	945109824	UCDVYQ4Zhbm3S2dlz7P1GBDg
6	MrBeast Gaming	892078757	UCIPPMRA040LQr5QPyJEbmXA
7	NBA	733364643	UCWJ2lWNubArHWmf3FIHbfcQ
8	BANGTANTV	727648334	UCLkAepWjdylmXSltofFvsYQ
9	Marvel Entertainment	701862407	UCvC4D8onUfXzvjTOM-dBfEA
10	Dude Perfect	636788063	UCRijo3ddMTht_IHyNSNXpNQ
11	Big Hit Labels	599584464	UCUaT_39o1x6qWjz7K2pWcgw
12	Beast Reacts	562235109	UCmBA_wu8xGg1OfOkfW13Q0Q
13	Bad Bunny	540900050	UCmS75G-98QihSusY7NfCZtw
14	Bizarrap	489131667	UCjmJDM5pRKbUlVIzDYYWb6g
15	Warner Bros. Pictures	483263857	UCke6I9N4KfC968-yRcd5YRg
16	SSundee	466972707	UCz97F7dMxBNOfGYu3rx8aCw
17	Sony Pictures Entertainment	466378833	UCpB959t8iPrxQWj7G6n0ctQ
18	SSSniperWolf	462433311	UCt8z2S30Wl-GQEluFVM8NUw
19	Apple	448863763	UCE_M8A5yxnLfW0KghEeajjw

	channelTitle	occurences	channelId
2443	NFL	124	UCDVYQ4Zhbm3S2dlz7P1GBDg
2419	NBA	114	UCWJ2lWNubArHWmf3FIHbfcQ
1155	FOX Soccer	57	UCooTLkxcpnTNx6vfOovfBFA
2428	NBC Sports	50	UCqZQlzSHbVJrwrn5XvzrzcA
2952	Ryan Trahan	46	UCnmGIkw-KdI0W5siakKPKog
551	CBS Sports Golazo	33	UCET00YnetHT7tOpu12v8jxg
346	Beast Reacts	32	UCUaT_39o1x6qWjz7K2pWcgw
1339	Genshin Impact	32	UCiS882YPwZt1NfaM0gR0D9Q
4244	videogamedunkey	31	UCsvn_Po0SmunchJYOWpOxMg
3970	ZHC Crafts	31	UCPAk4rqVIwg1NCXh61VJxbg
3455	The Game Theorists	30	UCo_IB5145EVNcf8hw1Kku7w
2422	NBA on TNT	30	UCU7iRrk3xfpUk0R6VdyC1Ow
303	BWF TV	29	UChh-akEbUM8_6ghGVnJd6cQ
710	Clash of Clans	29	UCD1Em4q90ZUK2R5HKesszJg
1219	First We Feast	29	UCPD_bxCRGpmmeQcbe2kpPaA
3060	SeaWattgaming	29	UCSpfz1IyUA1NBH-cgj8ygUw
2222	Marvel Entertainment	28	UCvC4D8onUfXzvjTOM-dBfEA
1005	Dude Perfect	28	UCRijo3ddMTht_IHyNSNXpNQ
4164	morgans vlogs	28	UC-vaBe-YMpvcZL5rQ5OopZw
3955	YoungBoy Never Broke Again	26	UClW4jraMKz6Qj69lJf-tODA

	video_id	title	publishedAt	channelId	channelTitle	categoryId	trending_date	tags	view_count	likes	dislikes	comment_count	thumbnail_link	comments_disabled	ratings_disabled	description	category_title
152788	gQlMMD8auMs	BLACKPINK - ‘Pink Venom’ M/V	2022-08-19 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-09-10 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	277791741	12993894	0	3534337	https://i.ytimg.com/vi/gQlMMD8auMs/default.jpg	False	False	BLACKPINK - ‘Pink Venom’ M/VKick in the door W...	Music
56374	WMweEpGlu_U	BTS (방탄소년단) 'Butter' Official MV	2021-05-21 03:46:13+00:00	UC3IZKseVpdzPSBaWxBxundA	HYBE LABELS	10	2021-05-30 00:00:00+00:00	BIGHIT\|빅히트\|방탄소년단\|BTS\|BANGTAN\|방탄	264407389	16021534	150989	6738537	https://i.ytimg.com/vi/WMweEpGlu_U/default.jpg	False	False	BTS (방탄소년단) 'Butter' Official MV Credits: Dire...	Music
3358	gdZLi9oWNZg	BTS (방탄소년단) 'Dynamite' Official MV	2020-08-21 03:58:10+00:00	UC3IZKseVpdzPSBaWxBxundA	Big Hit Labels	10	2020-08-28 00:00:00+00:00	BIGHIT\|빅히트\|방탄소년단\|BTS\|BANGTAN\|방탄	232649205	15735533	714194	6065230	https://i.ytimg.com/vi/gdZLi9oWNZg/default.jpg	False	False	BTS (방탄소년단) 'Dynamite' Official MVCredits:Dire...	Music
73564	hdmx71UjBXs	Turn into orbeez - Tutorial #Shorts	2021-07-03 04:04:57+00:00	UCt8z2S30Wl-GQEluFVM8NUw	FFUNTV	24	2021-08-08 00:00:00+00:00	[None]	206202284	6840430	240769	2826	https://i.ytimg.com/vi/hdmx71UjBXs/default.jpg	False	False	Turn into orbeez - Tutorial #ShortsHey guys! W...	Entertainment
4980	vRXZj0DzXIA	BLACKPINK - 'Ice Cream (with Selena Gomez)' M/V	2020-08-28 04:00:11+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2020-09-05 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	184778248	11795670	879354	2735997	https://i.ytimg.com/vi/vRXZj0DzXIA/default.jpg	False	False	BLACKPINK - ‘Ice Cream (with Selena Gomez)’Com...	Music
159786	POe9SOEKotk	BLACKPINK - ‘Shut Down’ M/V	2022-09-16 04:00:12+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2022-10-15 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	180654898	8438151	0	1326586	https://i.ytimg.com/vi/POe9SOEKotk/default.jpg	False	False	BLACKPINK - ‘Shut Down’Blackpink in your areaB...	Music
198978	YudHcBIxlYw	JISOO - ‘꽃(FLOWER)’ M/V	2023-03-31 04:00:14+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2023-04-29 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	170333822	8553612	0	1162689	https://i.ytimg.com/vi/YudHcBIxlYw/default.jpg	False	False	JISOO - ‘꽃(FLOWER)’ ABC 도레미만큼 착했던 나그 눈빛이 싹 변했지...	Music
179180	CocEMWdc7Ck	SHAKIRA \|\| BZRP Music Sessions #53	2023-01-12 00:00:07+00:00	UCmS75G-98QihSusY7NfCZtw	Bizarrap	24	2023-01-20 00:00:00+00:00	bizarrap\|biza\|bisa\|bizzarrap\|bzrp\|bzrp music s...	158477831	8333879	0	468245	https://i.ytimg.com/vi/CocEMWdc7Ck/default.jpg	False	False	SHAKIRA \|\| BZRP Music Sessions #53Lyrics by: h...	Entertainment
68979	CuklIb9d3fI	BTS (방탄소년단) 'Permission to Dance' Official MV	2021-07-09 03:59:12+00:00	UC3IZKseVpdzPSBaWxBxundA	HYBE LABELS	10	2021-07-16 00:00:00+00:00	HYBE\|HYBE LABELS\|하이브\|하이브레이블즈	156482499	12117314	102132	2781218	https://i.ytimg.com/vi/CuklIb9d3fI/default.jpg	False	False	BTS (방탄소년단) 'Permission to Dance' Official MVC...	Music
81347	awkkyBH2zEo	LISA - 'LALISA' M/V	2021-09-10 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2021-09-16 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	154134590	11348978	113448	2402692	https://i.ytimg.com/vi/awkkyBH2zEo/default.jpg	False	False	LISA - LALISA내 뒷모습만 봐도 알잖아어두워질 때 분홍빛이나새하얀 조명이 ...	Music
21367	-5q5mZbe3V8	BTS (방탄소년단) 'Life Goes On' Official MV	2020-11-20 04:58:11+00:00	UC3IZKseVpdzPSBaWxBxundA	Big Hit Labels	10	2020-11-28 00:00:00+00:00	BIGHIT\|빅히트\|방탄소년단\|BTS\|BANGTAN\|방탄	150622781	11405030	126202	4160903	https://i.ytimg.com/vi/-5q5mZbe3V8/default.jpg	False	False	BTS (방탄소년단) 'Life Goes On' Official MVCredits:...	Music
118181	ia6fRSeK8I0	jai shree ram 🚩#shorts #ashortaday	2022-03-15 03:21:02+00:00	UCuIpkP1H2Vb_NFu8dLIWoPw	CHANDAN ART ACADEMY	27	2022-03-21 00:00:00+00:00	[None]	149615603	7940311	0	48945	https://i.ytimg.com/vi/ia6fRSeK8I0/default.jpg	False	False	NaN	Education
11764	dyRsYk0LyA8	BLACKPINK – ‘Lovesick Girls’ M/V	2020-10-02 04:00:13+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2020-10-09 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	140685439	9217876	127308	1507605	https://i.ytimg.com/vi/dyRsYk0LyA8/default.jpg	False	False	BLACKPINK – ‘Lovesick Girls’영원한 밤창문 없는 방에 우릴 가...	Music
91383	U3ASj1L6_sY	Adele - Easy On Me (Official Video)	2021-10-14 23:00:11+00:00	UComP_epzeKzvBX156r6pm1Q	AdeleVEVO	10	2021-11-05 00:00:00+00:00	There ain’t no gold\|In this river\|That I’ve be...	139547582	4714130	59433	241678	https://i.ytimg.com/vi/U3ASj1L6_sY/default.jpg	False	False	Official Video for Easy On Me by Adele.Shop th...	Music
199180	1WEAJ-DFkHE	$1 vs $500,000 Plane Ticket!	2023-04-01 20:00:04+00:00	UCX6OQ3DkcsbYNE6H8uQQuVA	MrBeast	24	2023-04-30 00:00:00+00:00	[None]	139409168	4810157	0	144548	https://i.ytimg.com/vi/1WEAJ-DFkHE/default.jpg	False	False	Check out ALL of MrBeast’s awesome jobs or dis...	Entertainment
187747	jZGpkLElSu8	KAROL G, Shakira - TQG (Official Video)	2023-02-24 05:00:09+00:00	UCz9yS18zJGQObwUL_K-ICnw	KarolGVEVO	10	2023-03-04 00:00:00+00:00	karol\|tqg\|tqg karol\|tqg shakira\|karol shakira\|...	138548083	5461423	0	199368	https://i.ytimg.com/vi/jZGpkLElSu8/default.jpg	False	False	KAROL G, Shakira - TQG (Official Video)Escucha...	Music
96555	0e3GPea1Tyg	$456,000 Squid Game In Real Life!	2021-11-24 21:00:01+00:00	UCX6OQ3DkcsbYNE6H8uQQuVA	MrBeast	24	2021-12-02 00:00:00+00:00	[None]	137068663	10926910	67027	527142	https://i.ytimg.com/vi/0e3GPea1Tyg/default.jpg	False	False	MAKE SURE YOU WATCH UNTIL GLASS BRIDGE IT'S IN...	Entertainment
54989	TDNNkOv8M8Q	INSANE strawberry trick! 😨 #shorts	2021-05-08 07:34:14+00:00	UC6D1L2vxEAg_Vi0JSxMBDgA	Dan Rhodes	24	2021-05-17 00:00:00+00:00	[None]	127913129	4244408	195737	29538	https://i.ytimg.com/vi/TDNNkOv8M8Q/default.jpg	False	False	NaN	Entertainment
67359	PRz64kSEJqs	She is foxy but not enough #Shorts	2021-06-29 00:47:43+00:00	UCt8z2S30Wl-GQEluFVM8NUw	Fortnite Fun TV	24	2021-07-08 00:00:00+00:00	[None]	126907932	4195786	139672	2660	https://i.ytimg.com/vi/PRz64kSEJqs/default.jpg	False	False	She is foxy but not enough #ShortsHey guys! Wa...	Entertainment
190583	HjBo--1n8lI	Rihanna’s FULL Apple Music Super Bowl LVII Hal...	2023-02-13 03:58:18+00:00	UCDVYQ4Zhbm3S2dlz7P1GBDg	NFL	17	2023-03-18 00:00:00+00:00	NFL\|Football\|American Football\|sport\|sports	113116792	2764210	0	150958	https://i.ytimg.com/vi/HjBo--1n8lI/default.jpg	False	False	Listen to Rihanna’s iconic hits in Spatial Aud...	Sports
127582	8dJyRm2jJ-U	PSY - 'That That (prod. & feat. SUGA of BTS)' MV	2022-04-29 09:00:10+00:00	UCrDkAvwZum-UTjHmzDI2iIw	officialpsy	10	2022-05-07 00:00:00+00:00	PSY\|싸이\|psy\|Psy\|박재상\|Comeback\|coming back\|9th\|PS...	111477556	6496912	0	353082	https://i.ytimg.com/vi/8dJyRm2jJ-U/default.jpg	False	False	PSY - 'That That (prod. & feat. SUGA of BTS)' ...	Music
66766	Fw7fbKoK3e8	MvRyhan Funny videos #tiktok #Shorts	2021-06-25 07:37:36+00:00	UCcFQLco2CA2uq9J2Uwcoi6Q	Mv Ryhan	24	2021-07-05 00:00:00+00:00	[None]	106089141	1866882	97235	7073	https://i.ytimg.com/vi/Fw7fbKoK3e8/default.jpg	False	False	#shorts	Entertainment
43374	CKZvWhCqx1s	ROSÉ - 'On The Ground' M/V	2021-03-12 05:00:15+00:00	UCOmHUn--16B90oW2L6FRR3A	BLACKPINK	10	2021-03-20 00:00:00+00:00	YG Entertainment\|YG\|와이지\|K-pop\|BLACKPINK\|블랙핑크\|블...	103691157	7244067	96144	1559327	https://i.ytimg.com/vi/CKZvWhCqx1s/default.jpg	False	False	On The GroundMy life's been magic seems fantas...	Music
89984	MbWq-EwUy_M	Dice Stacks from $1 to $100	2021-10-06 21:44:27+00:00	UChfTcl5XfdTUCjkfuro982Q	That's Amazing Shorts	17	2021-10-29 00:00:00+00:00	[None]	103564168	7174425	120961	23727	https://i.ytimg.com/vi/MbWq-EwUy_M/default.jpg	False	False	Dice Stacking Tricks from $1 to $100 #shorts	Sports
985	hsm4poTWjMs	Cardi B - WAP feat. Megan Thee Stallion [Offic...	2020-08-07 04:00:10+00:00	UCxMAbVFmxKUVGAll0WVGpFw	Cardi B	10	2020-08-16 00:00:00+00:00	Cardi B\|Cardi\|Atlantic Records\|rap\|hip hop\|tra...	98442414	3207729	467717	310630	https://i.ytimg.com/vi/hsm4poTWjMs/default.jpg	False	False	Cardi B - WAP feat. Megan Thee StallionStream/...	Music
126767	myjEoDypUD8	Watch the uncensored moment Will Smith smacks ...	2022-03-28 03:06:53+00:00	UCIRYBXDze5krPDzAEOxFGVA	Guardian News	25	2022-05-03 00:00:00+00:00	Jada Pinkett Smith\|Jada Pinkett Smith chris ro...	98202265	1443032	0	245566	https://i.ytimg.com/vi/myjEoDypUD8/default.jpg	False	False	Best actor nominee Will Smith appeared to slap...	News & Politics
115170	LrJYKxyrMwg	Hey man, we are Italian 🇮🇹😅🤷🏼‍♀️#shorts #funny...	2022-02-20 20:42:28+00:00	UCQFYC_kwJ_FSs5UvZryzDFQ	Jessi & Sean	22	2022-03-06 00:00:00+00:00	[None]	97611742	4005923	0	9645	https://i.ytimg.com/vi/LrJYKxyrMwg/default.jpg	False	False	NaN	People & Blogs
135776	kXpOEzNZ8hQ	BTS (방탄소년단) 'Yet To Come (The Most Beautiful M...	2022-06-10 03:59:38+00:00	UC3IZKseVpdzPSBaWxBxundA	HYBE LABELS	10	2022-06-17 00:00:00+00:00	HYBE\|HYBE LABELS\|하이브\|하이브레이블즈	93952431	9444379	0	2469783	https://i.ytimg.com/vi/kXpOEzNZ8hQ/default.jpg	False	False	BTS (방탄소년단) 'Yet To Come (The Most Beautiful M...	Music
61775	ggJoXFNkRUw	Turn into egg - Tutorial #Shorts	2021-05-23 19:29:35+00:00	UCt8z2S30Wl-GQEluFVM8NUw	Fortnite Fun TV	24	2021-06-13 00:00:00+00:00	[None]	92004215	2841950	103019	1865	https://i.ytimg.com/vi/ggJoXFNkRUw/default.jpg	False	False	Turn into egg - Tutorial #ShortsHey guys! Watc...	Entertainment
182581	TJ2ifmkGGus	1,000 Blind People See For The First Time	2023-01-28 21:00:00+00:00	UCX6OQ3DkcsbYNE6H8uQQuVA	MrBeast	24	2023-02-06 00:00:00+00:00	[None]	91624124	7787760	0	305146	https://i.ytimg.com/vi/TJ2ifmkGGus/default.jpg	False	False	If you would like to support more of this sigh...	Entertainment
56080	2Zcz3Z0baVE	HOW TO GO THROUGH THE DRESS CODE 👗🎀💂‍♂️\|\| #SHORTS	2021-05-15 18:29:43+00:00	UC63mNFJR8EAb8wAIJwoCmTA	5-Minute Crafts FAMILY	26	2021-05-23 00:00:00+00:00	5-Minute Crafts\|5-Minute Crafts Family\|family\|...	89075984	2293772	97541	13435	https://i.ytimg.com/vi/2Zcz3Z0baVE/default.jpg	False	False	#Shorts #YouTubeShorts...	Howto & Style
91374	O2W2gUXAt78	My hidden talent #shorts	2021-10-09 20:14:58+00:00	UCiJUp_NBW2D_UMQIvq2nlPg	Zach King Shorts	23	2021-11-05 00:00:00+00:00	shorts\|#shorts\|zach king\|magic\|tiktok\|dance\|fe...	87284105	2813557	64294	4402	https://i.ytimg.com/vi/O2W2gUXAt78/default.jpg	False	False	Not many people know about my hidden talent of...	Comedy
101782	CvCtn5Q_nzs	Crazy #alluarjun #painting #shorts #viral #tr...	2021-12-08 13:16:02+00:00	UCMmvhaKpOxeyneANESIYXcA	Dr.Harrsha Artist	1	2021-12-29 00:00:00+00:00	[None]	86415224	5676872	0	25975	https://i.ytimg.com/vi/CvCtn5Q_nzs/default.jpg	False	False	NaN	Film & Animation
55961	FLGCGc7sAUw	Bella Poarch - Build a B*tch (Official Music V...	2021-05-14 04:00:16+00:00	UCCY_8y1FjtOegxKB4s2bWqw	Bella Poarch	22	2021-05-22 00:00:00+00:00	bella poarch\|bella porch\|build a bitch\|build a...	84063330	5627368	162546	308370	https://i.ytimg.com/vi/FLGCGc7sAUw/default.jpg	False	False	Stream Build a B*tch: http://bellapoarch.lnk.t...	People & Blogs
67739	HwpUtagJ4PE	Oddly Satisfying Video #Shorts	2021-06-25 09:02:18+00:00	UCUzylqtbvZ8O4kL5FQb4bUA	Thanh Thảo Official	22	2021-07-10 00:00:00+00:00	[None]	83600439	2469516	123738	4934	https://i.ytimg.com/vi/HwpUtagJ4PE/default.jpg	False	False	Thanks for watching !Please like, share and su...	People & Blogs
49577	u4HYTp4sqH8	I broke my finger! 😨 (Behind the scenes) 😂 #sh...	2021-04-13 06:25:39+00:00	UC6D1L2vxEAg_Vi0JSxMBDgA	Dan Rhodes	24	2021-04-20 00:00:00+00:00	[None]	82000798	2525244	132813	13534	https://i.ytimg.com/vi/u4HYTp4sqH8/default.jpg	False	False	This one is crazy!	Entertainment
63187	XA2YEHn-A8Q	TWICE Alcohol-Free M/V	2021-06-09 08:58:12+00:00	UCaO6TYtlC8U5ttz62hTrZgg	JYP Entertainment	10	2021-06-16 00:00:00+00:00	TWICE\|트와이스\|taste of love\|alcoholfree\|alcoholfr...	81850570	2626749	60378	934021	https://i.ytimg.com/vi/XA2YEHn-A8Q/default.jpg	False	False	TWICE Alcohol-Free M/V TWICE The 10th Mini Alb...	Music
49144	-C-16oZxTbw	This is impossible! (Behind the scenes) 🤐 #sh...	2021-04-10 13:57:03+00:00	UC6D1L2vxEAg_Vi0JSxMBDgA	Dan Rhodes	24	2021-04-18 00:00:00+00:00	[None]	81514544	2616550	144498	15673	https://i.ytimg.com/vi/-C-16oZxTbw/default.jpg	False	False	Crazy trick!	Entertainment
46161	6swmTBVI83k	Lil Nas X - MONTERO (Call Me By Your Name) (Of...	2021-03-26 04:00:14+00:00	UCtTfSyci2urfwXXu_eRpNRA	LilNasXVEVO	10	2021-04-03 00:00:00+00:00	lilnasx\|montero\|lil nas x\|lil nas\|nas x\|call m...	79848249	3287141	290208	591103	https://i.ytimg.com/vi/6swmTBVI83k/default.jpg	False	False	Official video for “MONTERO (Call Me By Your N...	Music
175771	YxWlaYCA8MU	Jhoome Jo Pathaan Song \| Shah Rukh Khan, Deepi...	2022-12-22 05:30:09+00:00	UCbTLwN10NoCU4WDzLf1JMOA	YRF	10	2023-01-03 00:00:00+00:00	shah rukh khan\|deepika padukone\|pathaan song\|p...	79358096	2221125	0	163810	https://i.ytimg.com/vi/YxWlaYCA8MU/default.jpg	False	False	Can't stop ourselves from vibing to this absol...	Music

Analyzing Youtube trending data starting from August 2020 to April 2023¶

Table of Contents¶

1: Data Collection¶

2: Data Cleaning¶

3: Exploratory Data Analysis¶

4: Analysis, Hypothesis Testing, Machine Learning¶

5: Conclusions¶

Part 1: Data Collection¶

Introduction¶

Part 2: Data Cleaning¶

Part 3: Exploratory Data Analysis¶

Preliminary Graphs¶

Top 50 Videos¶

Word Cloud¶

Circle Packing Chart¶

Data Collection: Profile Picture Extraction from Youtube API¶

Data Cleanup: Cropping Images¶

Graphing¶

Part 4: Analysis, Hypothesis Testing and Machine Learning¶

Classification¶

What Makes a Video Trending?¶

Comparing Likes, Viewcount, and Comments¶

Part 5: Conclusions¶

1: Data Collection ¶

2: Data Cleaning ¶

3: Exploratory Data Analysis ¶

4: Analysis, Hypothesis Testing, Machine Learning ¶

5: Conclusions ¶